Ideogram API lists GPT Image and Nano Banana: what Sume's catalog adds
Ideogram's API overview now lists GPT Image and Nano Banana beside Ideogram 4.5. Here is how that compares with the models Sume's /v1/images catalog lists.
Yes. Ideogram's API overview (read 2026-10-06) says its API offers Ideogram 4.5, Ideogram 4.0, GPT Image and Nano Banana for images, and Seedance 2.5, MiniMax H3 and Kling for video. If you only want to call those families from one vendor, that page answers it. The page does not say which GPT Image or Nano Banana version it means, so check the model list before you plan a migration.
Sume covers the same ground with one difference in shape: a single POST /v1/images route and a catalog you can read at GET /v1/images/models.
What Sume's image catalog lists
Per the Sume Image API docs, the ids include ideogram/ideogram-v4.5, ideogram/ideogram-v3, openai/gpt-image-2.5, openai/gpt-image-2.5-sunburst, openai/gpt-image-2, google/nano-banana-2 and google/nano-banana-pro. The same catalog also lists Seedream, Flux 2, Qwen, Imagen 4, Recraft V4, Grok and Higgsfield Soul rows. sume/auto is a separate value that lets Sume choose.
Side by side
| Question | Ideogram API (vendor page) | Sume Image API |
|---|---|---|
| Image families | Ideogram 4.5 / 4.0, GPT Image, Nano Banana | Ideogram 4.5 / V3, GPT Image 2.5 (two variants) and 2, Nano Banana 2 / Pro, plus Seedream, Flux 2, Qwen, Imagen 4, Recraft, Grok, Soul |
| Mask on Ideogram 4.5 edit | Yes, optional mask | No. mask_url is listed only on the GPT Image 2.5 rows |
| Reference images on Ideogram 4.5 | Up to 4 beside the image to edit | First reference is the image to edit, up to 4 more (5 total) |
| Result URLs | Expire; download what you keep | Sume-hosted signed data[].url |
| Concurrency | 10 in-flight requests by default | Plan concurrency with a queue in front |
| Video | Seedance 2.5, MiniMax H3, Kling | Video router lists seedance-2.5 and minimax-h3-max among its models |
How to choose
- Need a mask on an Ideogram 4.5 edit: call Ideogram directly. On Sume, use a GPT Image 2.5 row for masked edits.
- Need one bill and one key across GPT Image, Nano Banana and Ideogram: use the Sume catalog and read prices per model from the endpoints call.
- Need more than the edit: Sume's catalog filter by
supported_parameterstells you before you spend which rows accept references, masks orbackground.
Check the catalog, not the headline
Catalogs move. A vendor page tells you what that vendor offers today, and the Sume catalog tells you what Sume serves today. Neither is a promise about next month.
Before a migration, call GET /v1/images/models and filter on the capability you need. The response lists each model's supported parameters, so you can see in one request whether a row accepts references, a mask or a background setting. Then call the endpoints route for the one you picked, which lists the price per image and the limits for that row.
If a model you want is not in the list, Sume does not run it. Pick the nearest listed row, or keep that call on the vendor.
Sources
Related posts
More in Comparisons
- Interactive AI video for enterprise: live avatar or quiz video?
Interactive can mean a live conversation or a quiz inside a video. A table of both from HeyGen's September guide, and which part a Sume avatar clip covers.
- Kling 4.0 or Seedance 2.5 for a 30-second AI video today?
Both advertise 30 seconds. Only one has a callable id on Sume today. A spec-by-spec read of the vendor pages and what you can actually request.
- Lemonfox TTS at $2.50 per million characters vs Sume: the honest gap
Lemonfox's page works out to about $2.50 per million characters. Sume lists $47.50. Cost for 900, 22,500 and 1M characters, and what the gap buys you.
- Lip-sync a video you have, or animate a photo: which API?
Re-syncing a mouth in footage and making a still talk are different jobs. A guide using Sync.so docs and Sume lip-sync, avatar and face-swap routes.
Written by Sume